Dataset for Stock Market Prediction

The historical stock prices of three petroleum companies: Pakistan State Oil (PSO), Hascol, and Attock Petroleum Limited (APL), are extracted from the Pakistan Stock Exchange (PSX) website through a web scrapper for the last four years. Different attributes related to the stocks of each of these companies are extracted for each day. We extract attributes like total volume of trade for a day, high price, close price, low price, and open price. Along with this, for each of these companies, Twitter data for sentiment analysis is extracted using Twint, which is an open-source web scraper written in Python. It offers to scrape unlimited tweets despite of limitations of Twitter API. After tweets extraction, we need the user’s profile-based attributes and tweet-based attributes to calculate the composite influence score of each user. Tweet ID retrieved from Twint is used to extract all these attributes using Twitter API ‘Tweepy’.